Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2011 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9050. Min Range: -2.9050
Max Act: 2.9050. Min Act: -0.1700
Data Index: 1139827 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9050. Min Range: -2.9050
Max Act: 2.8574. Min Act: -0.1700
Data Index: 850783 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9050. Min Range: -2.9050
Max Act: 2.8415. Min Act: -0.1700
Data Index: 669952 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9050. Min Range: -2.9050
Max Act: 2.8415. Min Act: -0.1700
Data Index: 328317 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9050. Min Range: -2.9050
Max Act: 2.8415. Min Act: -0.1700
Data Index: 203984 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9050. Min Range: -2.9050
Max Act: 2.8256. Min Act: -0.1700
Data Index: 612837 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9050. Min Range: -2.9050
Max Act: 2.8096. Min Act: -0.1700
Data Index: 1070884 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9050. Min Range: -2.9050
Max Act: 2.8415. Min Act: -0.1700
Data Index: 644760 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9050. Min Range: -2.9050
Max Act: 2.8574. Min Act: -0.1700
Data Index: 389737 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9050. Min Range: -2.9050
Max Act: 2.8415. Min Act: -0.1700
Data Index: 537940 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9050. Min Range: -2.9050
Max Act: 2.8096. Min Act: -0.1700
Data Index: 1003194 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9050. Min Range: -2.9050
Max Act: 2.8256. Min Act: -0.1700
Data Index: 573873 (C4 (Web Text))
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9050. Min Range: -2.9050
Max Act: 2.7937. Min Act: -0.1700
Data Index: 750743 (C4 (Web Text))
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9050. Min Range: -2.9050
Max Act: 2.8096. Min Act: -0.1700
Data Index: 595766 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9050. Min Range: -2.9050
Max Act: 2.7937. Min Act: -0.1700
Data Index: 1033781 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9050. Min Range: -2.9050
Max Act: 2.7937. Min Act: -0.1700
Data Index: 258334 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9050. Min Range: -2.9050
Max Act: 2.7937. Min Act: -0.1700
Data Index: 978607 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9050. Min Range: -2.9050
Max Act: 2.7937. Min Act: -0.1700
Data Index: 905893 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9050. Min Range: -2.9050
Max Act: 2.7778. Min Act: -0.1700
Data Index: 406566 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9050. Min Range: -2.9050
Max Act: 2.7937. Min Act: -0.1700
Data Index: 967872 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19